AI Paper Atlas

Research map / Graph learning / Graph self-supervised learning

GALOPA: Graph Transport Learning with Optimal Plan Alignment

Yejiang Wang, Yuhai Zhao, Daniel Zhengkui Wang, Ling Li

NeurIPS 2023 · Graph learning › Graph self-supervised learning · approach: Contrastive learning with negatives and views · 0 citations (OpenAlex)

Read the paper

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Align optimal transport plan instead of OT distance (ablation)GALOPA · CORAaccuracy: 0.795 -> 0.842Improved
Align optimal transport plan instead of OT distance (ablation)GALOPA · CITESEERaccuracy: 0.689 -> 0.743Improved
Align optimal transport plan instead of OT distance (ablation)GALOPA · PROTEINSaccuracy: 0.733 -> 0.769Improved
Align optimal transport plan instead of OT distance (ablation)GALOPA · MUTAGaccuracy: 0.851 -> 0.911Improved
Use node attributes only (ignore edge structure, rho=0, sigma=1) in the graph-space calibration signal (ablation)GALOPA · CORAaccuracy: 0.842 -> 0.776Hurt
Use node attributes only in the graph-space calibration signal (rho=0, sigma=1) (ablation)GALOPA · CITESEERaccuracy: 0.743 -> 0.647Hurt
Vary sigma from 1 to 0.5 to 0 (node attribute vs edge weighting) with rho!=0 (ablation)GALOPA · CORAaccuracy: 0.842 -> 0.835 -> 0.823No clear effect
Vary sigma from 1 to 0.5 to 0 with rho!=0 (ablation)GALOPA · MUTAGaccuracy: 0.91 -> 0.911 -> 0.868Mixed
Remove 80% of edges and destroy 80% of node attributes in augmentation (ablation)GALOPA · CITESEERaccuracy: 0.743 -> 0.742No clear effect
Heavy augmentation perturbation (edge perturbation plus feature masking) (ablation)GALOPA · PROTEINSaccuracyNo clear effect
Use GALOPA instead of best unsupervised baseline GCA/SimGRACE (ablation)GALOPA vs baselines · PUBMEDaccuracy (%): 80.89 -> 84.57Improved
Use GALOPA instead of SimGRACE (ablation)GALOPA vs baselines · TU graph datasets averageaccuracy (%): 77.31 -> 78.94Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy